All Posts

Notes from You and Your Research

Notes from “You and Your Research” lecture (pdf) by Richard Hamming:

Read more ...


Policy Gradient Demystified

This is a simple explanation of Policy Gradient algorithm in Reinforcement Learning (RL). First, some background of Supervised Learning is presented and then, Policy Gradient method is studied as an extension to the Supervised Learning formulation. The blog post will clarify some of the notations usually covered in Reinforcement Learning lectures and build the basics for studying advanced RL algorithms.

Read more ...


Humor Generation with Recurrent Neural Networks

Generating humor is quite a challenging problem in the domain of Computational Linguistics and Natural Language Processing. Humor is subjective and it can be interpreted in a large number of ways by different people. There have been attempts [1][2] to formalize humor from the perspective of Artificial Intelligence. However, the drawback of these methods is that they generate a very specific category of humor.

Read more ...


TMVA Project in Machine Learning

Being a Machine learning enthusiast, I was overjoyed when my Google Summer of Code proposal to CERN SFT was accepted. My project involved lot of understanding and research in the field of Machine Learning. I designed and implemented various feature extraction methods in the TMVA toolkit. This blog post details the work I have been doing on this project for the past 4 months with CERN members.

Read more ...


Autoencoders Implementation Design II

In this post, I’ll discuss in detail about the design and implementation of Autoencoder transformation in TMVA. I am making all the changes in the branch develop (initially it was autoencoder, I renamed it) of my fork. I’ll be adding all the new features in this branch only. All the code can later be merged from this branch.

Read more ...


Autoencoders Implementation Design I

In this post, I’d like to discuss the existing architecture of variable transformation.

Read more ...


Progress Update

Last two weeks, I mostly spent on learning ROOT tools and exploring ideas for showcasing VarTransform method by visual plots. One of the explored ideas that appealed me the most is Histogram i.e. displaying the variances of variables on a histogram and show the selected and rejected variables. Below is the kind of plot I had in mind:

Read more ...


Getting started with Variable Transformation

In the past two weeks, I had two meetings over Skype with my mentor Sergei Gleyzer. One was personal meet and other was a general meeting of all TMVA developers. The one to one personal meet was a short Skype call on 19th May. We discussed about the work done and the first task I’d be focussing on. On 27th May, we had our first kickoff session to mark the beginning of Google Summer of Code program and getting introduced to fellow TMVA developers and mentors. We explained our projects in short and reported our progress in the past weeks. It lasted for about 45 minutes and it was very motivational for me. All the mentors are really cool and positive. We’d be having such general meetings once or twice a month.

Read more ...


Google Summer of Code 2016 at CERN

My project proposal for Google Summer of Code 2016 has been accepted at CERN. It’s always been my passion to work in the field of Machine Learning and I am very grateful to CERN community for providing me this bright opportunity. I’ll be working on Toolkit for Multivariate Data Analysis (TMVA), a ROOT-integrated Machine Learning environment for the processing and parallel evaluation of sophisticated multivariate classification techniques. My project primarily focuses on Deep Learning which involves implementing an unsupervised feature extraction method with Autoencoders in TMVA toolkit. I’ll be also implementing dimensionality reduction techniques like Local Linear Embedding, Feature Agglomeration etc. which are useful for data analysis in high-energy physics. You can have a look at my project page here. Don’t forget to bookmark this page if you are following my project closely. I intend to use this blog to track and document progress of my project.

Read more ...